© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35479
    Prev
    Next
    INDEX
    Explanations

    brush/brushed/brushes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĹłæīĢ
    -0.11
    _AUX
    -0.11
     Alley
    -0.09
    erb
    -0.09
    éĶ·
    -0.09
    oping
    -0.09
     Alf
    -0.09
    пл
    -0.09
    äºİæѤ
    -0.09
    AZE
    -0.09
    POSITIVE LOGITS
    åĪ·
    0.12
     Brush
    0.11
    æİīäºĨ
    0.10
     brush
    0.10
    åĢĶ
    0.09
    اة
    0.09
    Brush
    0.09
    brush
    0.08
    æİī
    0.08
    yne
    0.08
    Activations Density 0.012%

    No Known Activations